diff --git a/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/ONNX_MODEL.md b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/ONNX_MODEL.md
new file mode 100644
index 0000000000..4ded5d315d
--- /dev/null
+++ b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/ONNX_MODEL.md
@@ -0,0 +1,57 @@
+
+[//]: # (Custom component imports)
+
+import DocString from '@site/src/components/DocString';
+import PythonCode from '@site/src/components/PythonCode';
+import AppDisplay from '@site/src/components/AppDisplay';
+import SectionBreak from '@site/src/components/SectionBreak';
+import AppendixSection from '@site/src/components/AppendixSection';
+
+[//]: # (Docstring)
+
+import DocstringSource from '!!raw-loader!./a1-[autogen]/docstring.txt';
+import PythonSource from '!!raw-loader!./a1-[autogen]/python_code.txt';
+
+<DocString>{DocstringSource}</DocString>
+<PythonCode GLink='AI_ML/LOAD_MODEL/ONNX_MODEL/ONNX_MODEL.py'>{PythonSource}</PythonCode>
+
+<SectionBreak />
+
+    
+
+[//]: # (Examples)
+
+## Examples
+
+import Example1 from './examples/EX1/example.md';
+import App1 from '!!raw-loader!./examples/EX1/app.json';
+
+
+
+<AppDisplay 
+    nodeLabel='ONNX_MODEL'
+    appImg={''}
+    outputImg={''}
+    >
+    {App1}
+</AppDisplay>
+
+<Example1 />
+
+<SectionBreak />
+  
+    
+
+[//]: # (Appendix)
+
+import Notes from './appendix/notes.md';
+import Hardware from './appendix/hardware.md';
+import Media from './appendix/media.md';
+
+## Appendix
+
+<AppendixSection index={0} folderPath='nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/'><Notes /></AppendixSection>
+<AppendixSection index={1} folderPath='nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/'><Hardware /></AppendixSection>
+<AppendixSection index={2} folderPath='nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/'><Media /></AppendixSection>
+
+
diff --git a/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/a1-[autogen]/docstring.txt b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/a1-[autogen]/docstring.txt
new file mode 100644
index 0000000000..902772f8a6
--- /dev/null
+++ b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/a1-[autogen]/docstring.txt
@@ -0,0 +1,41 @@
+ONNX_MODEL loads a serialized ONNX model and uses it to make predictions using ONNX Runtime.
+
+    This allows supporting a wide range of deep learning frameworks and hardware platforms.
+
+    Notes
+    -----
+
+    On the one hand, ONNX is an open format to represent deep learning models.
+    ONNX defines a common set of operators - the building blocks of machine learning
+    and deep learning models - and a common file format to enable AI developers
+    to use models with a variety of frameworks, tools, runtimes, and compilers.
+
+    See: https://onnx.ai/
+
+    On the other hand, ONNX Runtime is a high-performance inference engine for machine
+    learning models in the ONNX format. ONNX Runtime has proved to considerably increase
+    performance in inferencing for a broad range of ML models and hardware platforms.
+
+    See: https://onnxruntime.ai/docs/
+
+    Moreover, the ONNX Model Zoo is a collection of pre-trained models for common
+    machine learning tasks. The models are stored in ONNX format and are ready to use
+    in different inference scenarios.
+
+    See: https://github.com/onnx/models
+
+    Parameters
+    ----------
+    file_path : str
+        Path to a ONNX model to load and use for prediction.
+
+    default : Vector
+        The input tensor to use for prediction.
+        For now, only a single input tensor is supported.
+        Note that the input tensor shape is not checked against the model's input shape.
+
+    Returns
+    -------
+    Vector:
+        The predictions made by the ONNX model.
+        For now, only a single output tensor is supported.
diff --git a/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/a1-[autogen]/python_code.txt b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/a1-[autogen]/python_code.txt
new file mode 100644
index 0000000000..012554b48f
--- /dev/null
+++ b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/a1-[autogen]/python_code.txt
@@ -0,0 +1,62 @@
+from flojoy import flojoy, run_in_venv, Vector
+from flojoy.utils import FLOJOY_CACHE_DIR
+
+
+@flojoy
+@run_in_venv(
+    pip_dependencies=[
+        "onnxruntime",
+        "numpy",
+        "onnx",
+    ]
+)
+def ONNX_MODEL(
+    file_path: str,
+    default: Vector,
+) -> Vector:
+    
+
+    import os
+    import onnx
+    import urllib.request
+    import numpy as np
+    import onnxruntime as rt
+
+    model_name = os.path.basename(file_path)
+
+    if file_path.startswith("http://") or file_path.startswith("https://"):
+        # Downloading the ONNX model from a URL to FLOJOY_CACHE_DIR.
+        onnx_model_zoo_cache = os.path.join(
+            FLOJOY_CACHE_DIR, "cache", "onnx", "model_zoo"
+        )
+
+        os.makedirs(onnx_model_zoo_cache, exist_ok=True)
+
+        filename = os.path.join(onnx_model_zoo_cache, model_name)
+
+        urllib.request.urlretrieve(
+            url=file_path,
+            filename=filename,
+        )
+
+        # Using the downloaded file.
+        file_path = filename
+
+    # Pre-loading the serialized model to validate whether is well-formed or not.
+    model = onnx.load(file_path)
+    onnx.checker.check_model(model)
+
+    # Using ONNX runtime for the ONNX model to make predictions.
+    sess = rt.InferenceSession(file_path, providers=["CPUExecutionProvider"])
+
+    # TODO(jjerphan): Assuming a single input and a single output for now.
+    input_name = sess.get_inputs()[0].name
+    label_name = sess.get_outputs()[0].name
+
+    # TODO(jjerphan): For now NumPy is assumed to be the main backend for Flojoy.
+    # We might adapt it in the future so that we can use other backends
+    # for tensor libraries for application using Deep Learning libraries.
+    input_tensor = np.asarray(default.v, dtype=np.float32)
+    predictions = sess.run([label_name], {input_name: input_tensor})[0]
+
+    return Vector(v=predictions)
diff --git a/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/hardware.md b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/hardware.md
new file mode 100644
index 0000000000..7f78a555c4
--- /dev/null
+++ b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/hardware.md
@@ -0,0 +1 @@
+This node does not require any peripheral hardware to operate. Please see INSTRUMENTS for nodes that interact with the physical world through connected hardware.
\ No newline at end of file
diff --git a/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/media.md b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/media.md
new file mode 100644
index 0000000000..8bcee9be90
--- /dev/null
+++ b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/media.md
@@ -0,0 +1 @@
+No supporting screenshots, photos, or videos have been added to the media.md file for this node.
\ No newline at end of file
diff --git a/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/notes.md b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/notes.md
new file mode 100644
index 0000000000..04aded2ec9
--- /dev/null
+++ b/docs/nodes/AI_ML/LOAD_MODEL/ONNX_MODEL/appendix/notes.md
@@ -0,0 +1 @@
+No theory or technical notes have been contributed for this node yet.
\ No newline at end of file